Astronomical image time series classification using CONVolutional attENTION (ConvEntion)

被引:2
作者
Bairouk, Anass [1 ]
Chaumont, Marc [1 ,3 ]
Fouchez, Dominique [2 ]
Paquet, Jerome [4 ,5 ]
Comby, Frederic [1 ]
Bautista, Julian
机构
[1] Univ Montpellier, Lab Comp Sci Robot & Microelect Montpellier, 161 Rue Ada, F-34095 Montpellier, France
[2] Aix Marseille Univ, Ctr Particle Phys Marseilles, CNRS, IN2P3, 163 Ave Luminy,Case 902, F-13009 Marseille, France
[3] Univ Nimes, 5 Rue Docteur Georges Salan,CS 13019, F-30021 Nimes, France
[4] Paul Valery Univ Montpellier, Grp AMIS, 3 Rte Mende, F-34090 Montpellier, France
[5] CNRS, UMR TETIS, Land Environm Remote Sensing & Spatial Informat, INRAE,CIRAD, 500 Rue Jean Francois Breton, F-34000 Montpellier, France
基金
美国国家科学基金会; 美国安德鲁·梅隆基金会;
关键词
techniques: image processing; supernovae: general; surveys; TRANSIENTS;
D O I
10.1051/0004-6361/202244657
中图分类号
P1 [天文学];
学科分类号
0704 ;
摘要
Aims. The treatment of astronomical image time series has won increasing attention in recent years. Indeed, numerous surveys following up on transient objects are in progress or under construction, such as the Vera Rubin Observatory Legacy Survey for Space and Time (LSST), which is poised to produce huge amounts of these time series. The associated scientific topics are extensive, ranging from the study of objects in our galaxy to the observation of the most distant supernovae for measuring the expansion of the universe. With such a large amount of data available, the need for robust automatic tools to detect and classify celestial objects is growing steadily.Methods. This study is based on the assumption that astronomical images contain more information than light curves. In this paper, we propose a novel approach based on deep learning for classifying different types of space objects directly using images. We named our approach ConvEntion, which stands for CONVolutional attENTION. It is based on convolutions and transformers, which are new approaches for the treatment of astronomical image time series. Our solution integrates spatio-temporal features and can be applied to various types of image datasets with any number of bands.Results. In this work, we solved various problems the datasets tend to suffer from and we present new results for classifications using astronomical image time series with an increase in accuracy of 13%, compared to state-of-the-art approaches that use image time series, and a 12% increase, compared to approaches that use light curves.
引用
收藏
页数:10
相关论文
共 31 条
[31]   High speed, on-line 4D microscopy using continuously scanning white light interferometry with a high speed camera and real-time FPGA image processing [J].
Montgomery, P. ;
Anstotz, F. ;
Montagna, J. .
OPTICAL MEASUREMENT SYSTEMS FOR INDUSTRIAL INSPECTION VII, 2011, 8082